Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach

doi:10.1109/TCYB.2015.2399172

OPT OpenIR > 光谱成像技术研究室

	Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
	Liu, Li 1,2; Shao, Ling 1,2; Li, Xuelong3 ; Lu, Ke 4,5; Shao, L
作者部门	光学影像学习与分析中心
	2016
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	46 期号:1 页码:158-170
产权排序	3
摘要	Extracting discriminative and robust features from video sequences is the first and most critical step in human action recognition. In this paper, instead of using handcrafted features, we automatically learn spatio-temporal motion features for action recognition. This is achieved via an evolutionary method, i.e., genetic programming (GP), which evolves the motion feature descriptor on a population of primitive 3D operators (e.g., 3D-Gabor and wavelet). In this way, the scale and shift invariant features can be effectively extracted from both color and optical flow sequences. We intend to learn data adaptive descriptors for different datasets with multiple layers, which makes fully use of the knowledge to mimic the physical structure of the human visual cortex for action recognition and simultaneously reduce the GP searching space to effectively accelerate the convergence of optimal solutions. In our evolutionary architecture, the average cross-validation classification error, which is calculated by an support-vector-machine classifier on the training set, is adopted as the evaluation criterion for the GP fitness function. After the entire evolution procedure finishes, the best-so-far solution selected by GP is regarded as the (near-) optimal action descriptor obtained. The GP-evolving feature extraction method is evaluated on four popular action datasets, namely KTH, HMDB51, UCF YouTube, and Hollywood2. Experimental results show that our method significantly outperforms other types of features, either hand-designed or machine-learned.
文章类型	Article
关键词	Action Recognition Feature Extraction Feature Learning Genetic Programming (Gp) Spatio-temporal Descriptors
学科领域	Computer Science, Artificial Intelligence
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2015.2399172
收录类别	SCI ; EI
关键词[WOS]	PARTICLE SWARM OPTIMIZATION ; FEATURE-SELECTION ; CLASSIFICATION ; FEATURES ; INTERPOLATION ; ALGORITHM ; FRAMEWORK
语种	英语
WOS研究方向	Computer Science
项目资助者	Chinese Academy of Sciences(KGZD-EW-T03) ; National Natural Science Foundation of China(61125106)
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000367144300015
引用统计	被引频次：140[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/27736
专题	光谱成像技术研究室
通讯作者	Shao, L
作者单位	1.Nanjing Univ Informat Sci & Technol, Coll Elect & Informat Engn, Nanjing 210044, Jiangsu, Peoples R China 2.Northumbria Univ, Dept Comp Sci & Digital Technol, Newcastle Upon Tyne NE1 8ST, Tyne & Wear, England 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt Imagery Anal & Learning, Xian 710119, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 5.Beijing Ctr Math & Informat Interdisciplinary Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Li,Shao, Ling,Li, Xuelong,et al. Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(1):158-170.
APA	Liu, Li,Shao, Ling,Li, Xuelong,Lu, Ke,&Shao, L.(2016).Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach.IEEE TRANSACTIONS ON CYBERNETICS,46(1),158-170.
MLA	Liu, Li,et al."Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach".IEEE TRANSACTIONS ON CYBERNETICS 46.1(2016):158-170.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Learning Spatio-Temp（2314KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文